English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This paper improves contrastive learning for sentence embeddings from twoperspectives: handling dropout noise and addressing feature corruption.Specifically, for the first perspective, we identify that the dropout noisefrom negative pairs affects the model's performance. Therefore, we propose asimple yet effective method to deal with such type of noise. Secondly, wepinpoint the rank bottleneck of current solutions to feature corruption andpropose a dimension-wise contrastive learning objective to address this issue.Both proposed methods are generic and can be applied to any contrastivelearning based models for sentence embeddings. Experimental results on standardbenchmarks demonstrate that combining both proposed methods leads to a gain of1.8 points compared to the strong baseline SimCSE configured with BERT base.Furthermore, applying the proposed method to DiffCSE, another strongcontrastive learning based baseline, results in a gain of 1.4 points.

SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectives